The three-vessel view (3VV) is a standardized transverse scanning plane used in fetal cardiac ultrasound screening to measure the absolute and relative diameters of the pulmonary artery (PA), ascending aorta (Ao), and superior vena cava, as required. The PA/Ao ratio is used to support the diagnosis of congenital heart disease (CHD). However, vascular diameters are measured manually by examiners, which causes intra- and interobserver variability in clinical practice. In the present study, we aimed to develop an artificial intelligence-based method for the standardized and quantitative evaluation of 3VV. In total, 315 cases and 20 examiners were included in this study. We used the object-detection software YOLOv7 for the automated extraction of 3VV images and compared three segmentation algorithms: DeepLabv3+, UNet3+, and SegFormer. Using the PA/Ao ratios based on vascular segmentation, YOLOv7 plus UNet3+ yielded the most appropriate classification for normal fetuses and those with CHD. Furthermore, YOLOv7 plus UNet3+ achieved an arithmetic mean value of 0.883 for the area under the receiver operating characteristic curve, which was higher than 0.749 for residents and 0.808 for fellows. Our automated method may support unskilled examiners in performing quantitative and objective assessments of 3VV images during fetal cardiac ultrasound screening.

Objective physical function assessment is crucial for determining patient eligibility for treatment and adjusting the treatment intensity. Existing assessments, such as performance status, are not well standardized, despite their frequent use in daily clinical practice. This paper explored how artificial intelligence (AI) could predict physical function scores from various patient data sources and reviewed methods to measure objective physical function using this technology. This review included relevant articles published in English that were retrieved from PubMed. These studies utilized AI technology to predict physical function indices from patient data extracted from videos, sensors, or electronic health records, thereby eliminating manual measurements. Studies that used AI technology solely to automate traditional evaluations were excluded. These technologies are recommended for future clinical systems that perform repeated objective physical function assessments in all patients without requiring extra time, personnel, or resources. This enables the detection of minimal changes in a patient’s condition, enabling early intervention and enhanced outcomes.

Total anomalous pulmonary venous connection (TAPVC) is one of the most severe congenital heart defects; however, prenatal diagnosis remains suboptimal. A normal fetal heart has a junction between the pulmonary venous (PV) and left atrium (LA). In contrast, no junctions are observed in patients with TAPVC. In the present study, we attempted to visualize and detect fetal PV-LA connections using artificial intelligence (AI) trained on the fetal cardiac ultrasound videos of 100 normal cases and six TAPVC cases. The PV-LA aggregate area was segmented using the following three-dimensional (3D) segmentation models: SegResNet, Swin UNETR, MedNeXt, and SegFormer3D. The Dice coefficient and 95% Hausdorff distance were used to evaluate segmentation performance. The mean values of the shortest PV-LA distance (PLD) and major axis angle (PLA) in each video were calculated. These methods demonstrated sufficient performance in visualizing and detecting the PV-LA connection. In terms of TAPVC screening performance, MedNeXt-PLD and SegResNet-PLA achieved mean area under the receiver operating characteristic curve values of 0.844 and 0.840, respectively. Overall, this study shows that our approach can support unskilled examiners in capturing the PV-LA connection and has the potential to improve the prenatal detection rate of TAPVC.

The clinical application of artificial intelligence (AI) can provide technical support for examiners and improve obstetric workflow efficiency. In this study, we developed AI models that automatically extract the four-chamber view (4CV) from fetal cardiac ultrasound videos and compute the cardiothoracic area ratio, cardiac axis, and cardiac position for prenatal screening of congenital heart disease. Fetal cardiac ultrasound videos from 301 patients in the second trimester were analyzed. The 4CV was automatically extracted using YOLOv7, followed by image segmentation with UNet 3+ and SegFormer, after which automated parameter calculation and estimation were performed. A clinical comparison study involving 22 obstetricians was conducted to evaluate the screening performance of the AI models. The models demonstrated stable performance in both normal and abnormal cases, including examinations acquired using different ultrasound systems. Furthermore, the AI models achieved screening performance comparable to that of expert obstetricians. These findings indicate that the proposed AI framework enables reliable 4CV extraction and accurate biometric parameter computation. This fully automated approach has the potential to reduce missed abnormalities and improve the consistency of fetal cardiac ultrasound screening.

In the original publication [1], there was a mistake in relation to the cited references:8

Total anomalous pulmonary venous connection (TAPVC) is a severe congenital heart disease, yet its prenatal detection rate remains suboptimal. To support prenatal ultrasound screening of TAPVC, the post-left atrium space (PLAS) index and the left-atrial posterior-space-to-diagonal (LAPSD) ratio measured in the four-chamber view (4CV) have been proposed as useful biometric parameters. In this study, we developed a novel approach that integrates automated 4CV extraction (AE) from fetal cardiac ultrasound videos with automated measurement of these indices. The heart, crux, and descending aorta were segmented using DeepLabv3+, UNet3+, and SegFormer. The screening performance of the AE-based methods was comparable to that of manual 4CV extraction, as demonstrated by similar mean areas under the receiver operating characteristic curve (AUCs). In a clinical comparison study, the mean AUC values for residents, fellows, experts, AE-DeepLabv3+, AE-UNet3+, and AE-SegFormer were 0.784, 0.801, 0.996, 0.903, 0.928, and 0.940, respectively, for the PLAS index and 0.797, 0.801, 0.996, 0.919, 0.916, and 0.940, respectively, for the LAPSD ratio. Although experts demonstrated the best overall performance, the fully automated methods consistently outperformed both the residents and fellows. This approach may support less experienced examiners, improve screening accuracy, streamline clinical workflows, and ultimately enhance the prenatal detection of TAPVC.